Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 804 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.1235. Min Range: -6.1235

Max Act: 6.1235. Min Act: -0.0000

Data Index: 1511217 (Python Code)

Max Activating Token Index: 778

Text #1

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.5647. Min Act: -0.0000

Data Index: 1640764 (Python Code)

Max Activating Token Index: 526

Text #2

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.5509. Min Act: -0.0000

Data Index: 1641327 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.1407. Min Act: -0.0000

Data Index: 1608626 (Python Code)

Max Activating Token Index: 761

Text #4

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.2095. Min Act: -0.0000

Data Index: 1387966 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.3248. Min Act: -0.0000

Data Index: 1393867 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.3123. Min Act: -0.0000

Data Index: 1464061 (Python Code)

Max Activating Token Index: 653

Text #7

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.1252. Min Act: -0.0000

Data Index: 1584983 (Python Code)

Max Activating Token Index: 811

Text #8

Max Range: 6.1235. Min Range: -6.1235

Max Act: 4.3615. Min Act: -0.0000

Data Index: 1437499 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 6.1235. Min Range: -6.1235

Max Act: 4.8078. Min Act: -0.0000

Data Index: 1531960 (Python Code)

Max Activating Token Index: 631

Text #10

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.1448. Min Act: -0.0000

Data Index: 1531221 (Python Code)

Max Activating Token Index: 1000

Text #11

Max Range: 6.1235. Min Range: -6.1235

Max Act: 4.9511. Min Act: -0.0000

Data Index: 1649279 (Python Code)

Max Activating Token Index: 543

Text #12

Max Range: 6.1235. Min Range: -6.1235

Max Act: 4.3492. Min Act: -0.0000

Data Index: 1604677 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.4095. Min Act: -0.0000

Data Index: 1482382 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.2340. Min Act: -0.0000

Data Index: 1486684 (Python Code)

Max Activating Token Index: 400

Text #15

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.1948. Min Act: -0.0000

Data Index: 1378070 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.2549. Min Act: -0.0000

Data Index: 1591015 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.1939. Min Act: -0.0000

Data Index: 1536499 (Python Code)

Max Activating Token Index: 982

Text #18

Max Range: 6.1235. Min Range: -6.1235

Max Act: 5.1725. Min Act: -0.0000

Data Index: 1582831 (Python Code)

Max Activating Token Index: 791

Text #19

Max Range: 6.1235. Min Range: -6.1235

Max Act: 4.9930. Min Act: -0.0000

Data Index: 1363885 (Python Code)

Max Activating Token Index: 508